Routine Modeling with Time Series Metric Learning

Paul Compagnon (1, 2) , Grégoire Lefebvre (2) , Stefan Duffner (1) , Christophe Garcia (1)

1 imagine - Extraction de Caractéristiques et Identification
2 Orange Labs [Meylan]

Traditionally, the automatic recognition of human activities is performed with supervised learning algorithms on limited sets of specific activities. This work proposes to recognize recurrent activity patterns, called routines, instead of precisely defined activities. The modeling of routines is defined as a metric learning problem, and an architecture, called SS2S, based on sequence-to-sequence models is proposed to learn a distance between time series. This approach only relies on inertial data and is thus non intrusive and preserves privacy. Experimental results show that a clustering algorithm provided with the learned distance is able to recover daily routines.

Mots clés: Sequence-to-Sequence Model; Activity Recognition; Time Series; Inertial data; Activity Recog- nition; Metric Learning

Domaines: Intelligence artificielle [cs.AI]; Réseau de neurones [cs.NE]

Paul Compagnon, Grégoire Lefebvre, Stefan Duffner, Christophe Garcia. Routine Modeling with Time Series Metric Learning. 28th International Conference on Artificial Neural Networks, Sep 2019, Munich, Germany. ⟨10.1007/978-3-030-30484-3_47⟩. ⟨hal-02165265v2⟩